© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 149
    Prev
    Next
    INDEX
    Explanations

    descriptions related to construction and architectural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    factors associated with roofing materials and their installation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    underneath or below a surface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyrchwyd
    -0.71
    RenderAtEndOf
    -0.70
    inigungs
    -0.57
     pinulongan
    -0.55
     باخ
    -0.54
    TagMode
    -0.53
    */),
    -0.53
    KeySpec
    -0.52
     muzzle
    -0.51
     FetchType
    -0.50
    POSITIVE LOGITS
    Above
    0.72
     floors
    0.72
     floor
    0.70
     Above
    0.69
     underneath
    0.69
     below
    0.68
     basement
    0.68
     subsoil
    0.66
     crawls
    0.66
     Beneath
    0.64
    Activations Density 0.054%

    No Known Activations